用大模型自动完成流体仿真与后处理，非专家也能操作。
MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing
- 通过思维链分解任务，让大模型按步骤完成复杂仿真
- 在新基准上实现86.9%成功率，耗时仅0.15美元/案例
- 适合工程人员快速上手仿真，降低专业门槛
计算流体动力学（CFD）广泛应用于航空航天、能源和生物领域，用于模拟流体流动、传热和化学反应。尽管大语言模型（LLMs）已在多个领域取得突破，但在复杂任务如后处理中的应用仍受限。为此，我们提出MetaOpenFOAM 2.0，采用思维链（COT）分解与迭代验证机制，支持通过自然语言输入实现非专家用户对仿真的自动化操作。在涵盖流体流动、传热、燃烧的仿真及提取、可视化等后处理的新基准测试中，其可执行性得分为6.3/7，成功率高达86.9%，显著优于前代版本（2.1/7，0%）。系统平均成本仅为0.15美元/案例。消融实验证明，基于思维链的任务分解与迭代优化是性能提升的关键。规模定律分析显示，增加思维链步骤可提高准确率，但相应增加令牌消耗，符合大模型后训练阶段的缩放规律。这些结果凸显了大模型在工业与科研中自动化CFD工作流的巨大潜力。代码已开源：https://github.com/Terry-cyx/MetaOpenFOAM
原文摘要 · Abstract (English)
Computational Fluid Dynamics (CFD) is widely used in aerospace, energy, and biology to model fluid flow, heat transfer, and chemical reactions. While Large Language Models (LLMs) have transformed various domains, their application in CFD remains limited, particularly for complex tasks like post-processing. To bridge this gap, we introduce MetaOpenFOAM 2.0, which leverages Chain of Thought (COT) decomposition and iterative verification to enhance accessibility for non-expert users through natural language inputs. Tested on a new benchmark covering simulation (fluid flow, heat transfer, combustion) and post-processing (extraction, visualization), MetaOpenFOAM 2.0 achieved an Executability score of 6.3/7 and a pass rate of 86.9%, significantly outperforming MetaOpenFOAM 1.0 (2.1/7, 0%). Additionally, it proved cost-efficient, averaging $0.15 per case. An ablation study confirmed that COT-driven decomposition and iterative refinement substantially improved task performance. Furthermore, scaling laws showed that increasing COT steps enhanced accuracy while raising token usage, aligning with LLM post-training scaling trends. These results highlight the transformative potential of LLMs in automating CFD workflows for industrial and research applications. Code is available at https://github.com/Terry-cyx/MetaOpenFOAM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。